R Notebook

library(tidyverse)

movies <- read.csv("archive/tmdb_5000_movies.csv")

head(movies)

names(movies)

1

First thoughts - homepage - missing values - revenue - 0 value - few factor types

2

movies_selected <-movies %>% 
  select(title,runtime, budget)
movies_selected

3

# count the number of missing values in each column
movies_selected %>% 
  summarise(across(.fns = ~sum(is.na(.x))))

movies_selected %>% 
  summarise(na_runtime = sum(is.na(runtime)),
            na_title = sum(is.na(title)),
            na_budget = sum(is.na(budget)))

4

movies_runtime <- movies_selected %>%
  mutate(runtime = na_if(runtime, 0))

movies_runtime %>% 
  summarise(count_missing = sum(is.na(runtime)))

5

movies_imputed <- movies_runtime %>% 
  mutate(runtime = coalesce(runtime, median(runtime, na.rm = TRUE)))

movies_imputed %>% 
  summarise(count_missing = sum(is.na(runtime)))

6

movies_imputed %>% 
  slice_min(runtime, n = 10)

7

# Overwrites movies_imputed to contain new budget values

movies_imputed <- movies_imputed %>%
  mutate(budget = if_else(budget < 100, median(budget), budget))

Extension 1

movie_budgets <- movies_imputed %>% 
  mutate(budget_type = case_when(budget < 12e6 ~ "Small budget",
                                 budget < 40e6 ~ "Meium budget", #Budgets between 12 and 40 million as ‘Medium budget’
                                 #budget > 12e6 & budget < 40e6 ~ "Medium budget",
                                 budget >= 40e6 ~ "Big budget"))
movie_budgets

2

movies %>%
  summarise(across(where(is.numeric), ~sum(is.na(.x))))

# summarises the number of missing values cross all columns of type character

movies %>%
  summarise(across(where(is.character), ~sum(is.na(.x))))